[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"sanity-rqsMC75TCZ2rryT-T3qF1X1w5l1w1zvGAEQB4wz-pwM":3},{"data":4,"sourceMap":-1},{"info":5,"latest":14,"pinned":191},{"_createdAt":6,"_id":7,"_rev":8,"_type":9,"_updatedAt":6,"descriptionText":10,"slug":11,"title":13},"2023-05-23T16:43:21Z","wp-tagcat-data-scraping","9HpbCsT2tq0xwozQfkc4ih","blogTag",null,{"current":12},"data-scraping","data scraping",[15,75,123,161],{"_id":16,"author":17,"commentCount":30,"comments":31,"excerpt":32,"featureTag":10,"image":33,"publishedAt":36,"slug":37,"sponsored":10,"tags":39,"title":74},"e2c3a8fc-0e6e-4851-abd3-3b1f5ae4f24e",[18],{"_id":19,"avatar":20,"name":25,"role":26,"slug":27},"dbdef9f7-acce-4431-8f4f-c2025df1c8c8",{"_type":21,"asset":22},"image",{"_ref":23,"_type":24},"image-5f1073fdcf2ebde7fee8570769d9d82d21573870-2316x3088-jpg","reference","Phoebe Sajor","Content Associate",{"_type":28,"current":29},"slug","phoebe-sajor",0,true,"Ryan hosts Akamai data scientist Robert Lester on the show to discuss how the growth of AI bots affects internet traffic, the ways these AI bots differ from the original search engine optimization ones, and why you might not want to mitigate AI bots on your websites.",{"_type":21,"asset":34},{"_ref":35,"_type":24},"image-d2cb4c948681d5ccbb8ff46ed2d69c6f6b6a8990-800x420-jpg","2026-01-06T08:40:00.000Z",{"_type":28,"current":38},"search-engine-bots-crawled-so-ai-bots-could-run",[40,44,48,53,57,64,66,70],{"_createdAt":6,"_id":41,"_rev":8,"_type":9,"_updatedAt":6,"slug":42,"title":43},"wp-tagcat-se-tech",{"current":43},"se-tech",{"_createdAt":6,"_id":45,"_rev":8,"_type":9,"_updatedAt":6,"slug":46,"title":47},"wp-tagcat-se-stackoverflow",{"current":47},"se-stackoverflow",{"_createdAt":6,"_id":49,"_rev":8,"_type":9,"_updatedAt":6,"slug":50,"title":52},"wp-tagcat-podcast",{"current":51},"podcast","The Stack Overflow Podcast",{"_createdAt":6,"_id":54,"_rev":8,"_type":9,"_updatedAt":6,"slug":55,"title":56},"wp-tagcat-bots",{"current":56},"bots",{"_createdAt":6,"_id":58,"_rev":59,"_type":9,"_updatedAt":60,"slug":61,"title":63},"wp-tagcat-ai","fpDTFQqIDjNJIbHDKPBGpV","2025-01-30T16:19:01Z",{"current":62},"ai","AI",{"_createdAt":6,"_id":7,"_rev":8,"_type":9,"_updatedAt":6,"slug":65,"title":13},{"current":12},{"_createdAt":6,"_id":67,"_rev":8,"_type":9,"_updatedAt":6,"slug":68,"title":69},"wp-tagcat-search",{"current":69},"search",{"_createdAt":6,"_id":71,"_rev":8,"_type":9,"_updatedAt":6,"slug":72,"title":73},"wp-tagcat-data",{"current":73},"data","Search engine bots crawled so AI bots could run",{"_id":76,"author":77,"commentCount":87,"comments":31,"excerpt":88,"featureTag":10,"image":89,"publishedAt":93,"slug":94,"sponsored":10,"tags":96,"title":122},"a876dbb4-3206-4b7c-bee8-04cc7a4f7405",[78],{"_id":79,"avatar":80,"name":83,"role":84,"slug":85},"wp-author-295",{"_type":21,"asset":81},{"_ref":82,"_type":24},"image-d670f8093b43e483a52ba692d929578633f70eb5-1024x1024-jpg","Eira May","B2B Editor",{"current":86},"emay",1,"Or Lenchner, CEO of Bright Data, joins Ben and Ryan for a deep-dive conversation about the evolving landscape of web data. They talk through the challenges involved in data collection, the role of synthetic data in training large AI models, and how public data access is becoming more restrictive. Or also shares his thoughts on the importance of transparency in data practices, the likely future of data regulation, and the philosophical implications of more people using AI to innovate and solve problems. ",{"_type":21,"asset":90,"attribution":92},{"_ref":91,"_type":24},"image-56c6dab9c7d1b66bc662c5f43ea9573418d94d17-2400x1260-webp","Alexandra Francis","2024-11-08T08:40:00.000Z",{"_type":28,"current":95},"one-of-the-world-s-biggest-web-scrapers-has-some-thoughts-on-data-ownership",[97,99,101,103,105,107,111,116,118],{"_createdAt":6,"_id":41,"_rev":8,"_type":9,"_updatedAt":6,"slug":98,"title":43},{"current":43},{"_createdAt":6,"_id":45,"_rev":8,"_type":9,"_updatedAt":6,"slug":100,"title":47},{"current":47},{"_createdAt":6,"_id":49,"_rev":8,"_type":9,"_updatedAt":6,"slug":102,"title":52},{"current":51},{"_createdAt":6,"_id":58,"_rev":59,"_type":9,"_updatedAt":60,"slug":104,"title":63},{"current":62},{"_createdAt":6,"_id":71,"_rev":8,"_type":9,"_updatedAt":6,"slug":106,"title":73},{"current":73},{"_createdAt":6,"_id":108,"_rev":8,"_type":9,"_updatedAt":6,"slug":109,"title":110},"wp-tagcat-training",{"current":110},"training",{"_createdAt":6,"_id":112,"_rev":8,"_type":9,"_updatedAt":6,"slug":113,"title":115},"wp-tagcat-data-ethics",{"current":114},"data-ethics","data ethics",{"_createdAt":6,"_id":7,"_rev":8,"_type":9,"_updatedAt":6,"slug":117,"title":13},{"current":12},{"_createdAt":6,"_id":119,"_rev":8,"_type":9,"_updatedAt":6,"slug":120,"title":121},"wp-tagcat-llm",{"current":121},"llm","One of the world’s biggest web scrapers has some thoughts on data ownership",{"_id":124,"author":125,"commentCount":30,"comments":31,"excerpt":130,"featureTag":10,"image":131,"publishedAt":133,"slug":134,"sponsored":10,"tags":136,"title":160},"699a2c40-381d-4427-8cbe-4e4c1638669f",[126],{"_id":79,"avatar":127,"name":83,"role":84,"slug":129},{"_type":21,"asset":128},{"_ref":82,"_type":24},{"current":86},"Josh Zhang, a staff site reliability engineer at Stack Overflow, tells Ryan and Eira how the Stack Exchange network defends against scraping bots. They also cover the emergence of human botnets, why DDoS attacks have spiked in the last couple of years, and the constant balancing act of protecting sites from attack without inhibiting legitimate users.",{"_type":21,"asset":132,"attribution":92},{"_ref":91,"_type":24},"2024-07-30T07:40:00.000Z",{"_type":28,"current":135},"how-stack-overflow-fends-off-scraping-bots",[137,139,141,143,147,152,154,158],{"_createdAt":6,"_id":41,"_rev":8,"_type":9,"_updatedAt":6,"slug":138,"title":43},{"current":43},{"_createdAt":6,"_id":45,"_rev":8,"_type":9,"_updatedAt":6,"slug":140,"title":47},{"current":47},{"_createdAt":6,"_id":49,"_rev":8,"_type":9,"_updatedAt":6,"slug":142,"title":52},{"current":51},{"_createdAt":6,"_id":144,"_rev":8,"_type":9,"_updatedAt":6,"slug":145,"title":146},"wp-tagcat-sre",{"current":146},"sre",{"_createdAt":6,"_id":148,"_rev":8,"_type":9,"_updatedAt":6,"slug":149,"title":151},"wp-tagcat-ddos",{"current":150},"ddos","DDoS",{"_createdAt":6,"_id":54,"_rev":8,"_type":9,"_updatedAt":6,"slug":153,"title":56},{"current":56},{"_createdAt":6,"_id":155,"_rev":8,"_type":9,"_updatedAt":6,"slug":156,"title":157},"wp-tagcat-security",{"current":157},"security",{"_createdAt":6,"_id":7,"_rev":8,"_type":9,"_updatedAt":6,"slug":159,"title":13},{"current":12},"How Stack Overflow fends off scraping bots",{"_id":162,"author":163,"commentCount":87,"comments":31,"excerpt":168,"featureTag":10,"image":169,"publishedAt":172,"slug":173,"sponsored":10,"tags":175,"title":190},"wp-post-20323",[164],{"_id":79,"avatar":165,"name":83,"role":84,"slug":167},{"_type":21,"asset":166},{"_ref":82,"_type":24},{"current":86},"The home team convenes to discuss the full public release of AI pair programmer GitHub Copilot, the VPN company that turned off subscriptions to protect its customers’ privacy, and the moral hazard of “free-to-play” apps and games.",{"_type":21,"asset":170},{"_ref":171,"_type":24},"image-472725c034235a56301dc8caf0ed41b3d298c57a-1200x630-png","2022-06-28T04:40:00.000Z",{"current":174},"github-copilot-is-here-but-whats-the-price-ep-457",[176,178,183,185],{"_createdAt":6,"_id":7,"_rev":8,"_type":9,"_updatedAt":6,"slug":177,"title":13},{"current":12},{"_createdAt":6,"_id":179,"_rev":8,"_type":9,"_updatedAt":6,"slug":180,"title":182},"wp-tagcat-github-copilot",{"current":181},"github-copilot","github copilot",{"_createdAt":6,"_id":49,"_rev":8,"_type":9,"_updatedAt":6,"slug":184,"title":52},{"current":51},{"_createdAt":6,"_id":186,"_rev":8,"_type":9,"_updatedAt":6,"slug":187,"title":189},"wp-tagcat-the-stack-overflow-podcast",{"current":188},"the-stack-overflow-podcast","the stack overflow podcast","GitHub Copilot is here. But what’s the price? (Ep. 457)",[]]